Mistral-7B-v0.1

7.24B parameters, text in, text out, 32K tokens of context. 1 provider serves it.

Verified 2026-10-25 Rank #90 in LLMs · score 100.8 method v1 Sources 3 Downloads 30d 327.2k · #210 of 619 tracked

Can I run it?4.3GB at INT4Estimatefits a 16 GB cardmethodCommunity: Mistral-7B-v0.1 - VRAM, Specs & Benchmarks →

Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24

Do people use it?327.2kdownloads, 30 days#210 of 619 we track · top 34%+6 likes, downloads −2% this week4,226 likesHugging Face2026-10-24

Worth reading

Picked by rule from 7 tracked pieces: the lab's own post, the most shared, a field report, the latest.

The lab's own post

Mistral 7B v0.1

Mistral enables organizations to retain full control over intellectual property, data, and decision logic within their own infrastructure.

mistral.ai 2023-09-27 1 HN pts 458 words

Latest · 3 years ago

Mistral AI “drops” mistral-7B-v0.1

twitter.com 2023-09-27 9 HN pts · 1 comments

7 best of 7 tracked

The 3 picks above, plus these 4. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

ArticlePerformance evaluation of DeepSeek-7B-chat and Mistral ...researchgate.net · undated
ArticleMistral-7B-v0.1 Open-Source LLM: Evaluation, Deployment & Commercial Use | DEV.codev.co · undated
Articlehttps://replicate.com/mistralai/mistral-7b-v0.1/readmereplicate.com · undated
ArticleMistral-7B-v0.1 - VRAM, Specs & Benchmarksapxml.com · undated

Where to run it

Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.

#	Cheapest live row	In /1M	Out /1M	Context	Quant	Seen
1	Featherless	—	—	—	—	Oct 25

All 1 provider →

Where it's used

Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.

Served by 1 API provider; heavily run locally (195 quantized builds); a big base for builders (3,800 fine-tunes, adapters and merges).

As a service1Featherless
On own hardware195quantized builds
Built on3,800943 fine-tunes · 2,467 adapters · 390 merges
In apps100+Hugging Face Spaces

Top Spaces running it: Vokturz/can-it-run-llm ♥ 1,053 · ehristoforu/mistral-7b-chat ♥ 80 · overhead520/LLM-Settings-Guide ♥ 79 · Vision-CAIR-Admin/MiniGPT4-video ♥ 46

Will it fit?

Weights only, an estimate: leave room for the KV cache. Method

Fits a 16 GB card at INT4

About 4.3 GB at INT4, 8.7 GB at FP8, 17 GB at BF16: weights only, so leave room for the KV cache.

Estimate params × bytes per param × 1.2 · how we estimate

The story so far

Weights, every dated article, and repo commits on one rail.

2 dated articles and 30 repo commits so far

Teal is the weights (2023-09-20), amber triangles are 2 dated articles (each links to it), grey ticks are repo commits.

What people built on it

3,995 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

3,995 derivatives on the Hub, most of them adapters

From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.

GGUF NousResearch/Hermes-2-Pro-Mistral-7B-GGUF for llama.cpp, Ollama, LM Studio 588.2k downloads GPTQ TheBloke/Mistral-7B-v0.1-GPTQ for vLLM, SGLang 223.5k downloads

All variants →

Reference

Everything else, folded: the full tables, every source.

What the card says

1 cited sentence

Summary generated, cited

The architecture utilizes Grouped-Query Attention and Sliding-Window Attention.^[1]

“Grouped-Query Attention”

Generated 2026-10-07 15:01 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.

Use-case evidence

1 use case

What it is good at 1 use case

Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.

Run on a laptop or phonestructuraldecision-model estimate p=0.89 fits: single-gpu

Facts

21 fields

Listed in LLMs

Facts

Mistral-7B-v0.1 has 7.24B parameters. (safetensors metadata, observed 2026-10-24)
Context length is 32,768 tokens (32K). (config.json max_position_embeddings, observed 2026-10-24)
License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
Created 2023-09-20, last modified 2025-07-24. (HF API, observed 2026-10-24)

Pipeline tag	text-generation
Library	transformers
Architectures	MistralForCausalLM
Model type	mistral
Dtype	bfloat16
Params by dtype	BF16: 7,241,732,096
Size band	M
MoE	no
Context length	32,768 (config.json max_position_embeddings)
Languages	en
Papers	arXiv:2310.06825
License	Apache 2.0 (apache-2.0)
Hub snapshot	2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · MistralForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · MistralForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed

vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for Mistral-7B-v0.1: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	17 GB · Single GPU (<24 GB)
FP8 (1 byte/param)	8.7 GB · Single GPU (<24 GB)
INT4 (0.5 bytes/param)	4.3 GB · Single GPU (<24 GB)

Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.

All variants

40 variants

Lineage

Original model Family: mistralai/Mistral-v0.1 3,995 derivatives on the Hub

finetune: 943quantized: 195adapter: 2,467merge: 390

Top variants (40 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
teknium/OpenHermes-2-Mistral-7B	finetune	—	—	—	apache-2.0	teknium	254	1.9M
openchat/openchat-3.5-0106	finetune	—	7.24B	M	apache-2.0	openchat	357	1.3M
GritLM/GritLM-7B	finetune	—	7.24B	M	apache-2.0	GritLM	122	649.9k
NousResearch/Hermes-2-Pro-Mistral-7B-GGUF	quantized	GGUF	—	—	apache-2.0	NousResearch	262	588.2k
NousResearch/Hermes-2-Pro-Mistral-7B	finetune	—	7.24B	M	apache-2.0	NousResearch	509	463.4k
dphn/dolphin-2.2.1-mistral-7b	finetune	—	7.24B	M	apache-2.0	dphn	197	432.7k
Intel/neural-chat-7b-v3-1	finetune	—	7.24B	M	apache-2.0	Intel	546	391k
HuggingFaceH4/mistral-7b-sft-beta	finetune	—	—	—	mit	HuggingFaceH4	25	413.5k
alignment-handbook/zephyr-7b-sft-full	finetune	—	7.24B	M	apache-2.0	alignment-handbook	27	386.2k
TheBloke/Mistral-7B-v0.1-GGUF	quantized	GGUF	—	—	apache-2.0	TheBloke	279	353.1k
NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF	quantized	GGUF	—	—	apache-2.0	NousResearch	95	358k
NousResearch/Nous-Hermes-2-Mistral-7B-DPO	finetune	—	7.24B	M	apache-2.0	NousResearch	222	346.6k
TheBloke/Mistral-7B-v0.1-GPTQ	quantized	GPTQ	7.24B	M	apache-2.0	TheBloke	37	223.5k
kaist-ai/mistral-orpo-capybara-7k	finetune	—	7.24B	M	mit	kaist-ai	26	169.6k
ibm-research/merlinite-7b	finetune	—	7.24B	M	apache-2.0	ibm-research	105	164.8k
TheBloke/Mistral-7B-v0.1-AWQ	quantized	AWQ	7.24B	M	apache-2.0	TheBloke	33	165.6k
MaziyarPanahi/Mistral-7B-v0.1-GGUF	quantized	GGUF	—	—	apache-2.0	MaziyarPanahi	0	163.3k
INSAIT-Institute/BgGPT-7B-Instruct-v0.2	finetune	—	7.29B	M	apache-2.0	INSAIT-Institute	25	104.8k
castorini/rank_zephyr_7b_v1_full	finetune	—	7.24B	M	mit	castorini	29	101.5k
predibase/gsm8k	adapter	—	—	—	—	predibase	4	94.7k
Locutusque/Hercules-2.5-Mistral-7B	finetune	—	7.24B	M	apache-2.0	Locutusque	7	87.8k
instructlab/merlinite-7b-lab	finetune	—	7.24B	M	apache-2.0	instructlab	22	63.2k
billborkowski/llava-NousResearch_Nous-Hermes-2-Vision-GGUF	quantized	GGUF	—	—	apache-2.0	billborkowski	24	61.3k
typeof/zephyr-7b-beta-lora	adapter	—	—	—	—	typeof	6	62k
scaleTech/myplaygirl-nsfw-classifier	finetune	—	142M	S	—	scaleTech	0	54.1k
NousResearch/Genstruct-7B	finetune	—	7.24B	M	apache-2.0	NousResearch	406	32k
NousResearch/Nous-Hermes-2-Vision-Alpha	finetune	—	—	—	apache-2.0	NousResearch	304	33.6k
NovusResearch/Thestral-0.1-tr-chat-7B	finetune	—	7.24B	M	apache-2.0	NovusResearch	3	47k
Rakuten/RakutenAI-7B	finetune	—	7.37B	M	apache-2.0	Rakuten	52	44.3k
Trendyol/Trendyol-LLM-7b-base-v1.0	finetune	—	7.34B	M	apache-2.0	Trendyol	16	44.5k
teknium/Mistral-Trismegistus-7B	finetune	—	—	—	apache-2.0	teknium	243	30.7k
Rijgersberg/GEITje-7B	finetune	—	—	—	apache-2.0	Rijgersberg	19	40k
cypienai/cymist-2-v02-SFT	finetune	—	7.24B	M	apache-2.0	cypienai	0	39.1k
Q-bert/Optimus-7B	finetune	—	7.24B	M	apache-2.0	Q-bert	13	38k
Kukedlc/Triunvirato-7b	merge	—	7.24B	M	apache-2.0	Kukedlc	1	36.2k
INC4AI/neural-chat-7b-v3	finetune	—	7.24B	M	apache-2.0	INC4AI	67	32.6k
teknium/CollectiveCognition-v1.1-Mistral-7B	finetune	—	—	—	apache-2.0	teknium	78	31.6k
predibase/glue_sst2	adapter	—	—	—	—	predibase	1	30.6k
Alphacode-AI/AlphaMist7B-slr-v1	finetune	—	7.24B	M	cc-by-nc-4.0	Alphacode-AI	0	30k
PsiPi/NousResearch_Nous-Hermes-2-Vision-GGUF	quantized	GGUF	—	—	apache-2.0	PsiPi	17	28.8k

Repository changelog

30 commits

Repository changelog 30 commits

Date	Commit	SHA
2025-07-24	Update README.md	27d67f1
2025-07-24	Update README.md	6284bd8
2025-07-24	Update README.md	93bc63f
2025-07-23	Update README.md	a15186d
2024-07-24	Update README.md	7231864
2024-07-24	Update README.md	ec2cce6
2024-07-04	Remove accidental chat template (this is a base model!)	f9824c3
2024-07-03	Align tokenizer with mistral-common (#158)	67b958e
2023-12-11	Adding `safetensors` variant of this model (#101)	26bca36
2023-12-08	Update tokenizer_config.json	1768803
2023-10-12	Add language (#56)	5e9c98b
2023-10-11	added arxiv	60e27e7
2023-10-09	Remove `added_tokens` json file (#44)	1fb9932
2023-10-05	Clarify Transformers version requirements	ae9d75c
2023-10-04	Upload tokenizer (#36)	f801b4a
2023-10-03	Disable normalization for special tokens (#26)	f966a60
2023-10-03	Update inference temperature	d00214e
2023-09-28	Update README.md (#15)	78814a9
2023-09-28	Update README.md	dbea3ef
2023-09-28	Update README.md	3c2faaa
2023-09-27	Update README.md	c927a0b
2023-09-27	Update README.md	bc5a33d
2023-09-27	Upload folder using huggingface_hub	e836d8f
2023-09-27	Update README.md	3c6e5d2
2023-09-27	more small updatey bois	29b3489
2023-09-27	Update small model card	eee9341
2023-09-27	Small updates	f592c5f
2023-09-26	Upload folder using huggingface_hub	0e5a0e2
2023-09-26	Upload folder using huggingface_hub	27f7f8c
2023-09-25	Upload folder using huggingface_hub	a8a9230

All providers

1 provider · 1 endpoint

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Mistral-7B-v0.1, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.

Provider	Model ref	Context	Quant	$/M in	$/M out	tok/s	TTFT	Tools	Status	Observed
Featherless hf	mistralai/Mistral-7B-v0.1	—	—	—	—	—	—	—	live	2026-10-25

Articles and coverage

7 pieces

Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.

Official1

Mistral 7B v0.1

mistral.ai2023-09-27officialauthorityHN 1 pts · 0 comments458 words

Mistral enables organizations to retain full control over intellectual property, data, and decision logic within their own infrastructure. ASML reports identifying sub-system errors 70% faster using Mistral's high-performance models, while BNP Paribas accelerates KYC processes from weeks to days. The European Patent Office reduces transcription time from days to minutes, and NATO partners with 20+ national government entities for secure AI deployment.written, reviewed, cited

Analysis5

Performance evaluation of DeepSeek-7B-chat and Mistral ...

researchgate.net

Mistral-7B-v0.1 Open-Source LLM: Evaluation, Deployment & Commercial Use | DEV.co

dev.co885 words

Mistral-7B-v0.1 is a 7.24B-parameter open-source language model from mistralai that employs grouped-query and sliding-window attention mechanisms. Inference requires Transformers library ≥4.34.0 and typically needs 16–24 GB VRAM, though int8/int4 quantization allows operation on 8–12 GB GPUs. The model operates under the Apache 2.0 license but lacks built-in moderation, requiring external guardrails for production safety.written, reviewed, cited

The model card explicitly states the model 'does not have any moderation mechanisms.'
Training a full model requires a setup with '≥40 GB multi-GPU' resources.

Mistral 7B v0.1 Specs, Benchmarks & Downloads - Bytetality

bytetality.com560 words

Mistral AI released Mistral 7B v0.1 on September 27, 2023, as an active text model with 7 billion parameters and an 8,192 token context window. The model requires a minimum RTX 3060 GPU with 12GB VRAM for local inference and operates under the Mistral License. It scores 30.5% on HumanEval coding tasks while achieving 81.3% on the HellaSwag reasoning benchmark.written, reviewed, cited

replicate.com59 words

Mistral-7B-v0.1 - VRAM, Specs & Benchmarks

apxml.com223 words

Community1

Mistral AI “drops” mistral-7B-v0.1

twitter.com2023-09-27HN 9 pts · 1 comments

Papers

1 paper

Papers 1

arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).

Mistral 7B this model

Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch +15 · 2023-10-10 · PDF · HF paper page (61 upvotes)

Similar models

3 models

Similar models

Llama-3.1-8B-Instruct · 8.03B
same size band (M), same task (text-generation), more providers
Qwen2.5-7B-Instruct · 7.62B
same size band (M), same task (text-generation), more providers, permissive license
Mistral-7B-Instruct-v0.2 · 7.24B
same size band (M), same task (text-generation), permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:33 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:01 UTC · Last verified 2026-10-25

Follow Mistral-7B-v0.1

Watch this model

/feeds/models/mistralai--Mistral-7B-v0.1.xml(RSS 2.0) · every change to Mistral-7B-v0.1
/feeds/families/mistralai--Mistral-v0.1.xml(RSS 2.0) · every change across the Mistral-v0.1 family

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.